PodParley PodParley

689: Observing LLMs in Production to Automatically Catch Issues

Arize's Amber Roberts and Xander Song join Jon Krohn this week, sharing invaluable insights into ML Observability, drift detection, retraining strategies, and the crucial task of ensuring fairness and ethical considerations in AI development.This episode is brought to you by Posit, the open-source data science company, by AWS Inferentia, and by Anaconda, the world's most popular Python distribution. Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast for sp...

An episode of the Super Data Science: ML & AI Podcast with Jon Krohn podcast, hosted by Jon Krohn, titled "689: Observing LLMs in Production to Automatically Catch Issues" was published on June 20, 2023 and runs 78 minutes.

June 20, 2023 ·78m · Super Data Science: ML & AI Podcast with Jon Krohn

0:00 / 0:00

Arize's Amber Roberts and Xander Song join Jon Krohn this week, sharing invaluable insights into ML Observability, drift detection, retraining strategies, and the crucial task of ensuring fairness and ethical considerations in AI development.This episode is brought to you by Posit, the open-source data science company, by AWS Inferentia, and by Anaconda, the world's most popular Python distribution. Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast for sponsorship information.In this episode you will learn:• What is ML Observability [05:07]• What is Drift [08:18]• The different kinds of model drift [15:31]• How frequently production models should be retrained? [25:15]• Arize's open-source product, Phoenix [30:49]• How ML Observability relates to discovering model biases [50:30]• Arize case studies [57:13]• What is a developer advocate [1:04:51]Additional materials: www.superdatascience.com/689

Arize's Amber Roberts and Xander Song join Jon Krohn this week, sharing invaluable insights into ML Observability, drift detection, retraining strategies, and the crucial task of ensuring fairness and ethical considerations in AI development.This episode is brought to you by Posit, the open-source data science company, by AWS Inferentia, and by Anaconda, the world's most popular Python distribution. Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast for sponsorship information.In this episode you will learn:• What is ML Observability [05:07]• What is Drift [08:18]• The different kinds of model drift [15:31]• How frequently production models should be retrained? [25:15]• Arize's open-source product, Phoenix [30:49]• How ML Observability relates to discovering model biases [50:30]• Arize case studies [57:13]• What is a developer advocate [1:04:51]Additional materials: www.superdatascience.com/689
Super Mamás Paulina and Bricia Lopez Top-rated podcast, hosted by sisters Paulina and Bricia Lopez. Super Mamas is a judgment-free space where new, expecting and experienced mothers come together to learn from one another. Laugh and cry along with the Super Mamas every week as they share stories with friends, experts and each other. Welcome to the Super Mamas Sisterhood! New episode every Tuesday. Featured on Oprah Daily, Parents Latina, Girlboss, Univision, Telemundo and NPR Super Literário Podcast Super Literário Podcast O podcast do Super Literário para discutir cinema, literatura e cultura pop Super Down Super Down Podcast More than 15% of people in the US are affected by Major Depressive Disorder, aka depression. Beyond the stigma and the black and white photos on tumblr, depression exists as a daily reality for many of us. Yet there are few voices discussing what daily life with depression is really like. We are here to change that, with consistent discussion, supportive & hopeful joy, and jokes. Lots of jokes. Join Will and Lauren as they discuss their experiences surviving day to day life, talk about current events in the world of depression, and offer up healthy activities for coping. The goal: hope for the depressed and knowledge for those who aren't. Always real, often relevant, occasionally preachy - This is Super Down. Super TRUEper TRUE Network Let’s spread a little #TRUElove.Get to know folks from all parts of TRUE Network on a deeper level. In typical TRUE style, we talk work, family, share personal stories and have a great time. We promise a little laughter and a dose of positivity. TRUE Love
URL copied to clipboard!